1. A scenic spot tourist flow prediction method comprises the following steps:

obtaining a historical visitor flow time series, wherein the historical visitor flow time series comprises a plurality of dates and corresponding visitor flow on the same day;

calculating time delay corresponding to the historical tourist flow time sequence based on an interactive information method;

calculating the historical tourist flow time series and the embedding dimension corresponding to the time delay based on a geometric invariant method;

performing phase space reconstruction on the historical visitor flow time series based on the time delay and the embedding dimension to obtain a plurality of corresponding phase space time series;

and inputting the plurality of phase space time sequences into a tourist amount prediction model so as to determine the predicted scenic spot tourist flow corresponding to the people flow prediction date by the tourist amount prediction model.

2. The method of claim 1, wherein after inputting the plurality of facies space time series to a tourist volume prediction model to determine a predicted scenic spot tourist volume by the tourist volume prediction model corresponding to a people volume prediction date, the method further comprises:

receiving a scenic spot tourist capacity query request from a client;

and responding to the scenic spot tourist volume query request, and sending the predicted scenic spot tourist volume to the client.

3. The method of claim 2, wherein after inputting the plurality of facies space time series to a tourist volume prediction model to determine a predicted scenic spot tourist volume by the tourist volume prediction model corresponding to a people volume prediction date, the method further comprises:

detecting whether the predicted scenic spot tourist volume exceeds a preset tourist volume threshold value or not;

when the number of the tourists exceeds the preset tourist number threshold value, pushing a scenic spot congestion notification to the corresponding client according to the information of each client device in the reserved client list; and the reservation client list records client device information corresponding to each tourist who makes a reservation on the people flow prediction date for going out.

4. The method of claim 1, wherein after inputting the plurality of facies space time series to a tourist volume prediction model to determine a predicted scenic spot tourist volume by the tourist volume prediction model corresponding to a people volume prediction date, the method further comprises:

acquiring the actually measured tourist flow corresponding to the pedestrian flow prediction date based on the scenic spot gate; the scenic spot gate is positioned at the entrance of the scenic spot and is used for performing ticket verification operation on persons entering the garden;

calculating a difference value of the tourist flow between the actually measured tourist flow and the predicted scenic spot tourist flow;

and when the difference value of the tourist flow exceeds a preset threshold value, generating a model optimization warning notice.

5. The method of claim 1, wherein the inputting the plurality of facies space time series to a tourist volume prediction model for determining a predicted scenic spot tourist volume by the tourist volume prediction model corresponding to a people volume prediction date comprises:

dividing the historical visitor flow time sequence according to the date type to obtain a corresponding holiday type subsequence and a corresponding workday type subsequence;

acquiring a target date type corresponding to the people flow prediction date;

selecting a target subsequence corresponding to the target date type from the holiday type subsequence and the workday type subsequence;

determining a tourist quantity prediction model corresponding to the target date type from a plurality of candidate tourist quantity prediction models; each candidate passenger capacity prediction model is provided with a corresponding date type;

and inputting the target subsequence into the determined tourist volume prediction model to obtain the predicted scenic spot tourist volume corresponding to the people volume prediction date.

6. The method of claim 1, wherein the guest prediction model comprises a first network module, a second network module, and a third network module in cascade,

the first network module is used for receiving the characteristic data corresponding to the phase space time sequence and processing the characteristic data through a first activation function, the second network module is used for performing matrix calculation processing on the input data, and the third network module is used for processing the input data through a second activation function so as to output the predicted scenic spot tourist flow.

7. The method of claim 6, wherein prior to inputting the plurality of facies space time series to a tourist mass prediction model, the method further comprises:

acquiring a first parameter interval, a second parameter interval and a third parameter interval which respectively correspond to network layer parameters of the first network module, the second network module and the third network module; wherein, the network layer parameters comprise network layer weight values and threshold values;

sampling M times from the first parameter interval, the second parameter interval and the third parameter interval according to a Latin hypercube sampling rule to obtain corresponding M sampling parameter sets; wherein M is a natural number greater than 1;

respectively defining corresponding population members based on the sampling parameter sets to construct corresponding populations;

determining an optimal population member from the population based on a training sample set and a preset population genetic algorithm;

and setting corresponding network layer parameters of the first network module, the second network module and the third network module by using the optimal population member.

8. A scenic spot tourist flow prediction apparatus comprising:

an acquisition unit configured to acquire a historical visitor volume time series including a plurality of dates and corresponding visitor volumes of the day;

the delay calculation unit is configured to calculate time delay corresponding to the historical tourist flow time series based on an interactive information method;

an embedding dimension calculation unit configured to calculate embedding dimensions corresponding to the historical tourist flow time series and the time delay based on a geometric invariant method;

a phase space reconstruction unit configured to perform phase space reconstruction on the historical guest traffic time series based on the time delay and the embedding dimension to obtain a corresponding plurality of phase space time series;

a tourist flow prediction unit configured to input the plurality of phase space time series to a tourist flow prediction model to determine a predicted scenic spot tourist flow corresponding to a person flow prediction date by the tourist flow prediction model.

9. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1-7.

10. An electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of the method according to any of claims 1-7 when executing the computer program.

Background

With the continuous improvement of the living standard of domestic residents, tourism has become an essential important project for entertainment and leisure in the lives of numerous Chinese people. Scenic spot traffic has been a particular concern for people and scenic spot management, for example, if visitors are able to predict in advance the likelihood of the concentration of a certain scenic spot, so that the visitors can better schedule or adjust their own itineraries.

At present, in order to predict scenic spot pedestrian volume, some experts and scholars propose that a statistical model or some existing artificial intelligence models can be used for identifying the pedestrian volume, but the statistical model is generally a linear model, and the problem of nonlinear correlation of the predicted scenic spot tourist volume can cause larger prediction error. In addition, some experts and scholars propose that the artificial intelligence model can be used for predicting the scenic spot passenger flow, but the conventional artificial intelligence model (such as an SVM) is easy to generate an over-fitting defect, so that the current artificial intelligence model is trapped into local optimization, and the accuracy of a passenger flow prediction result is influenced.

Disclosure of Invention

In view of this, embodiments of the present application provide a method and an apparatus for predicting a scenic spot visitor flow rate, so as to solve the problem in the prior art that the accuracy of a result of predicting a visitor flow rate in a scenic spot is low.

A first aspect of an embodiment of the present application provides a method for predicting a scenic spot visitor flow, including: obtaining a historical visitor flow time series, wherein the historical visitor flow time series comprises a plurality of dates and corresponding visitor flow on the same day; calculating time delay corresponding to the historical tourist flow time sequence based on an interactive information method; calculating the historical tourist flow time series and the embedding dimension corresponding to the time delay based on a geometric invariant method; performing phase space reconstruction on the historical visitor flow time series based on the time delay and the embedding dimension to obtain a plurality of corresponding phase space time series; and inputting the plurality of phase space time sequences into a tourist amount prediction model so as to determine the predicted scenic spot tourist flow corresponding to the people flow prediction date by the tourist amount prediction model.

A second aspect of the embodiments of the present application provides a scenic spot tourist traffic prediction apparatus, including: an acquisition unit configured to acquire a historical visitor volume time series including a plurality of dates and corresponding visitor volumes of the day; the delay calculation unit is configured to calculate time delay corresponding to the historical tourist flow time series based on an interactive information method; an embedding dimension calculation unit configured to calculate embedding dimensions corresponding to the historical tourist flow time series and the time delay based on a geometric invariant method; a phase space reconstruction unit configured to perform phase space reconstruction on the historical guest traffic time series based on the time delay and the embedding dimension to obtain a corresponding plurality of phase space time series; a tourist flow prediction unit configured to input the plurality of phase space time series to a tourist flow prediction model to determine a predicted scenic spot tourist flow corresponding to a person flow prediction date by the tourist flow prediction model.

A third aspect of embodiments of the present application provides a computer-readable storage medium, in which a computer program is stored, which, when executed by a processor, implements the steps of the method as described above.

A fourth aspect of embodiments of the present application provides a server, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method as described above when executing the computer program.

Compared with the prior art, the embodiment of the application has the advantages that:

by counting a plurality of dates and corresponding daily visitor flow to obtain a time sequence, and performing phase space reconstruction on the time sequence, time information in visitor data of a nonlinear visitor flow prediction problem can be better extracted, and the corresponding phase space time sequences are input into a visitor flow prediction model, so that the accuracy of the predicted scenic spot visitor flow can be effectively improved.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiments or the prior art descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.

Fig. 1 shows a flowchart of an example of a scenic spot tourist traffic prediction method according to an embodiment of the present application;

FIG. 2 illustrates a flow diagram of an example of parameter setting for a guest quantity prediction model according to an embodiment of the present application;

FIG. 3 illustrates a flow diagram of an example of determining predicted scenic spot guest traffic using a guest traffic prediction model in accordance with an embodiment of the present application;

fig. 4 is a block diagram showing a configuration of an example of a scenic spot passenger flow amount prediction apparatus according to an embodiment of the present application;

fig. 5 is a schematic diagram of an example of an electronic device according to an embodiment of the present application.

Detailed Description

In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

It should be noted that the embodiments and features of the embodiments may be combined with each other without conflict.

The invention may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The invention may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.

As used herein, a "module," "system," and the like are intended to refer to a computer-related entity, either hardware, a combination of hardware and software, or software in execution. In particular, for example, an element may be, but is not limited to being, a process running on a processor, an object, an executable, a thread of execution, a program, and/or a computer. Also, an application or script running on a server, or a server, may be an element. One or more elements may be in a process and/or thread of execution and an element may be localized on one computer and/or distributed between two or more computers and may be operated by various computer-readable media. The elements may also communicate by way of local and/or remote processes based on a signal having one or more data packets, e.g., from a data packet interacting with another element in a local system, distributed system, and/or across a network in the internet with other systems by way of the signal.

Finally, it should be further noted that the terms "comprises" and "comprising," when used herein, include not only those elements but also other elements not expressly listed or inherent to such processes, methods, articles, or devices. Without further limitation, an element defined by the phrase "comprising … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.

In addition, in the description of the present application, the terms "first," "second," "third," and the like are used solely to distinguish one from another and are not to be construed as indicating or implying relative importance.

Fig. 1 shows a flowchart of an example of a scenic spot tourist traffic prediction method according to an embodiment of the present application. Regarding the execution subject of the method of the embodiment of the present application, it may be a scenic server or a scenic tourism platform. The scenic spot tourism platform can not only complete the processing of relevant data and information in the scenic spot, but also perform communication interaction with other terminal equipment (for example, a terminal of a platform registered user) so as to realize various communication functions.

As shown in FIG. 1, in step 110, a historical guest traffic time series is obtained. Here, the historical visitor volume time series includes a plurality of dates and corresponding current day visitor volumes, which may be, for example, the number of scenic spot visitors to each day of the past half year.

In step 120, the time delay corresponding to the historical visitor flow time series is calculated based on the mutual information method. Here, the interactive information method can make up for the defect that the relevance of the front sequence point and the back sequence point is too strong in the autocorrelation method (or other delay determination methods), and the time delay suitable for the current data scene (i.e., the people flow prediction scene) is obtained by calculating the joint probability distribution and the system probability distribution.

In step 130, the embedding dimensions corresponding to the historical visitor flow time series and the time delay are calculated based on a geometric invariant method.

It should be understood that the state of a system at a time is referred to as a phase, and the geometric space that determines the state is referred to as a phase space. There are two key parameters in the phase space reconstruction technique: the embedded dimension d and the delay time τ. In practical applications, the time series is a finite sequence that is noisy, so that the embedding dimension d and the time delay τ must be chosen to be appropriate values according to the actual data.

Illustratively, some geometric invariants of the attractors (e.g., correlation dimension, Lyapunov exponent, etc.) may be computed and the dimension d may be gradually increased after the delay time τ is selected until they stop changing. From Takens' embedding theorem analysis, these geometric invariants have attractor geometric properties, and when dimension d is larger than the minimum embedding dimension, the geometry has been fully opened, when these geometric invariants are independent of the embedding dimension. Based on this theory, the embedding dimension d at which the geometric invariance of the attractor stops changing can be selected as the reconstructed phase space dimension.

In step 140, a phase space reconstruction is performed on the historical guest traffic time series based on the time delay and the embedding dimension to obtain a corresponding plurality of phase space time series.

In step 150, the plurality of phase space time series are input to a tourist volume prediction model to determine a predicted scenic spot tourist volume corresponding to the person volume prediction date by the tourist volume prediction model.

According to the embodiment of the application, the PSR technology is utilized to carry out phase space reconstruction on the historical tourist flow time sequence, the one-dimensional time sequence is reconstructed into a plurality of multidimensional sequences, and the phase space time sequence capable of better representing time information is obtained through the data mining process. Then, the phase space time series are input into the tourist prediction model, so that the tourist prediction model can accurately predict the scenic spot pedestrian volume of the corresponding date.

It should be noted that, unlike the conventional artificial intelligence model, a general artificial intelligence model can be implemented to have a processing capability for a corresponding task based on simple task sample training in order to process a classification problem, for example, an animal recognition model can be simply trained by using some animal image samples. However, when some practical natural problems are faced, since the influence factors are numerous or the uncertainty is large, the model cannot achieve the expected effect by directly using the initially prepared training sample set for training. In the service scenario of the embodiment of the present application, if the visitor volume of the visitors passing different dates is directly used as an input sample of the visitor volume prediction model, the influence of other external factors between different dates on the current day, such as temperature, air humidity, etc., cannot be fully considered. However, if different influence dimensions of the model are manually considered and set, a certain influence dimension may be omitted, resulting in a reduction in the accuracy of the prediction result of the model.

According to the method and the device, the historical visitor flow time sequence is mined by adopting a phase space reconstruction technology, time delay and corresponding embedding dimensionality are extracted, so that the path of the historical visitor flow time sequence in a high-dimensional space becomes clear, a plurality of phase space time sequences are constructed and input as models, and the visitor flow of scenic spots is predicted. Therefore, the reliability of the prediction result of the scenic spot passenger flow can be effectively guaranteed.

In some examples of embodiments of the present application, the tourist quantity prediction model comprises a first network module, a second network module and a third network module in cascade. Here, the first network module may represent an input module layer of the model, the second network module may represent a connection module layer of the model, and the third network module may represent an output module layer of the model. Specifically, the first network module is configured to receive feature data corresponding to the phase space time sequence and process the feature data through a first activation function, the second network module is configured to perform matrix calculation processing on the input data, and the third network module is configured to process the input data through a second activation function to output the predicted scenic spot visitor flow.

It should be noted that, in the process of setting and optimizing the tourist quantity prediction model, a general gradient optimization mode may be adopted to parameterize the model. However, the general gradient optimization method is only applicable to an artificial intelligence model corresponding to the classification problem, and when the method is used for the non-linear problem, the overfitting phenomenon is easy to occur.

Fig. 2 is a flowchart illustrating an example of parameter setting of a guest amount prediction model according to an embodiment of the present application.

As shown in fig. 2, in step 210, a first parameter interval, a second parameter interval, and a third parameter interval corresponding to network layer parameters of the first network module, the second network module, and the third network module, respectively, are obtained. Here, the network layer settings include network layer weights and thresholds. It should be understood that the weights and thresholds of the various network layers of the neural network may be continually adjusted during the training optimization until the model converges.

In step 220, M times of sampling are performed from the first parameter interval, the second parameter interval, and the third parameter interval according to the latin hypercube sampling rule to obtain corresponding M sampling parameter sets. Here, M is a natural number greater than 1. For example, a1, a2 and a3 may be sampled from the first parameter interval, the second parameter interval and the third parameter interval, respectively, to obtain corresponding sampling parameter sets { a1, a2 and a3}, and the sampling process may be repeated M times to obtain a final sampling result. Therefore, approximate random sampling from multivariate parameter distribution is realized through the hierarchical sampling technology of the Latin hypercube sampling rule, and the sampling requirements of different parameters of a multilayer structure in a model can be met.

In step 230, corresponding population members are respectively defined based on the respective sets of sampling parameters to construct corresponding populations.

In step 240, an optimal population member is determined from the population based on the training sample set and a preset population genetic algorithm.

It should be understood that Genetic Algorithm (GA) is designed and proposed according to the evolution law of organisms in nature, is a calculation model of the biological evolution process simulating natural selection and Genetic mechanism of darwinian biological evolution theory, and is a method for searching an optimal solution by simulating the natural evolution process. In addition, the type of population genetic algorithm used in the embodiments of the present application may be diversified, for example, the population genetic algorithm in other fields in the related art can be used as a reference, and should not be limited herein.

Illustratively, each training sample in the set of training samples may contain a phase space time series sample and a corresponding scenic spot visitor traffic label. And determining the fitness corresponding to each population member in the population by using a population fitness function, wherein the population fitness function can be defined by scenic spot tourist flow labels. The optimal population member with the highest fitness may then be determined from the population.

In step 250, the optimal population members are used to set the corresponding network layer parameters of the first network module, the second network module and the third network module. Specifically, the network layer parameters of the first network module, the second network module, and the third network module may be respectively and correspondingly set by using each parameter in the sampling parameter set corresponding to the optimal population member.

According to the method and the device, the tourist quantity prediction model is optimized by using the population genetic algorithm according with the evolution rule of the organism, the model can be effectively helped to find the global optimal solution in the training process, and compared with the gradient optimization algorithm, the problems of local optimal solution and overfitting can be effectively avoided.

It should be noted that the specific date types such as "legal holiday", "student cold and hot holiday" are one of the most important factors for scenic spot tourist traffic, for example, the revenue of many scenic spots in China mainly depends on the tourist traffic in the legal holiday.

In view of this, in some examples of embodiments of the present application, there are a plurality of candidate guest volume prediction models each having a corresponding date type, so as to invoke the corresponding candidate models for prediction operations for different prediction dates.

Fig. 3 illustrates a flow diagram of an example of determining predicted scenic spot guest traffic using a guest traffic prediction model according to an embodiment of the present application.

As shown in fig. 3, in step 310, the historical tourist volume time series is divided according to the date type to obtain a corresponding holiday type subsequence and a weekday type subsequence.

In step 320, a target date type corresponding to the people flow prediction date is obtained.

In step 330, a target subsequence corresponding to the target date type is selected from the holiday type subsequence and the workday type subsequence.

In step 340, a guest prediction model corresponding to the target date type is determined from the plurality of candidate guest prediction models. Here, each of the candidate guest capacity prediction models has a corresponding date type.

In step 350, the target subsequence is input to the determined tourist volume prediction model to obtain a predicted scenic spot tourist volume corresponding to the people volume prediction date.

In the embodiment of the application, different candidate models can be adopted for different date types of the prediction dates, and the time sequences of the corresponding date types are used for prediction, so that the holiday time sequences can be prevented from being used for reconstructing or predicting the scenic spot traffic of the working day, and the prediction result can be ensured to have higher accuracy.

In some cases, the term "people flow forecast date" may refer to a particular date relative to the current date (e.g., today or tomorrow), or may be a continuous date for a period of time, such as people flow forecasts for three days into the future (i.e., tomorrow, afterday, and grand afterday). It should be understood that, in order to ensure the accuracy of the prediction result, the people flow prediction date should not be too long different from the current date.

In some examples of embodiments of the application, after step 150, the method further comprises: and receiving a scenic spot passenger volume query request from the client. For example, before tourists travel to a scenic spot, the tourists may log in a scenic spot platform APP in advance, and generate a tourist amount query request for the scenic spot tourism platform by clicking a corresponding control. Then, in response to the scenic spot tourist volume query request, the scenic spot tourism platform sends the predicted scenic spot tourist volume to the client. Therefore, through data communication interactive operation between the client and the platform, tourists can know the people flow condition of the trip date (for example, the current day or the tomorrow) in advance, so that the tourists can plan and arrange a scenic spot trip plan, the situation that the tourists are crowded in the scenic spot can be avoided, and the tourism experience of the tourists in the scenic spot is guaranteed.

In some embodiments, it may also be detected whether the predicted scenic spot visitor volume exceeds a preset visitor volume threshold, and when the predicted scenic spot visitor volume exceeds the preset visitor volume threshold, a scenic spot congestion notification may be pushed to the corresponding client according to the information of each client device in the reserved client list. Here, the reservation client list records client device information corresponding to each guest who makes a reservation on the predicted flow rate date and makes a trip. Therefore, the jam risk notification can be timely pushed to the tourists who reserve to travel on the people flow prediction date, so that the tourists can have a certain psychological basis for the jam when visiting as an example, and the complaints of the tourists are reduced to the maximum extent.

In some cases, the prediction result of the model in the actual use scene may be unsatisfactory, for example, in practice, the number of people in the scenic spot is small but the scenic spot is predicted to be crowded, and in this case, the platform operator needs to be prompted to optimize the tourist amount prediction model.

Specifically, the actual passenger flow corresponding to the predicted pedestrian flow date can be collected based on the scenic spot gate. Here, the scenic spot gate is located at the entrance of the scenic spot and is used for performing ticket verification operation on the entering personnel. Illustratively, tourists can use a two-dimensional code on a mobile phone or a ticket to aim at a code scanning gun on a scenic spot gate, so that uploading and verification of ticket information are realized. Therefore, the corresponding actually measured tourist flow can be obtained by counting the tourist volume entering the garden at each scenic spot gate.

Then, a guest traffic difference between the measured guest traffic and the predicted scenic spot guest traffic may be calculated.

And then, when the difference value of the tourist volumes exceeds a preset threshold value, generating a model optimization warning notice, and reminding the platform operation and maintenance personnel to optimize the tourist volume prediction model based on the model optimization warning notice. For example, a model optimization warning notification may be sent to the terminal device corresponding to each platform operator to prompt the operator to optimize the model in time. Therefore, the deviation of the prediction result of the pedestrian volume caused by the performance problem or the site incompatibility problem of the tourist volume prediction model can be avoided, and the high accuracy of the scenic spot tourist volume prediction presented or pushed to the user is ensured.

Fig. 4 is a block diagram showing a configuration of an example of a scenic spot tourist flow predicting apparatus according to an embodiment of the present application.

As shown in fig. 4, the scenic spot guest flow volume prediction apparatus 400 includes an acquisition unit 410, a delay calculation unit 420, an embedding dimension calculation unit 430, a phase space reconstruction unit 440, and a guest flow volume prediction unit 450.

The obtaining unit 410 is configured to obtain a historical guest traffic time series including a plurality of dates and corresponding current day guest traffic.

The delay calculating unit 420 is configured to calculate a time delay corresponding to the historical tourist flow time series based on an interactive information method.

The embedding dimension calculating unit 430 is configured to calculate the embedding dimensions corresponding to the historical tourist flow time series and the time delay based on a geometric invariant method.

The phase space reconstruction unit 440 is configured to perform a phase space reconstruction on the historical guest traffic time series based on the time delay and the embedding dimension to obtain a corresponding plurality of phase space time series.

The tourist amount prediction unit 450 is configured to input the plurality of phase space time series to a tourist amount prediction model to determine a predicted scenic spot tourist amount corresponding to a person amount prediction date by the tourist amount prediction model.

It should be noted that, for the information interaction, execution process, and other contents between the above-mentioned devices/units, the specific functions and technical effects thereof are based on the same concept as those of the embodiment of the method of the present application, and specific reference may be made to the part of the embodiment of the method, which is not described herein again.

Fig. 5 is a schematic diagram of an example of an electronic device according to an embodiment of the present application. As shown in fig. 5, the electronic apparatus 500 of this embodiment includes: a processor 510, a memory 520, and a computer program 530 stored in the memory 520 and executable on the processor 510. The processor 510, when executing the computer program 530, implements the steps in the scenic spot passenger flow prediction method embodiments described above, such as the steps 110 to 150 shown in fig. 1. Alternatively, the processor 510, when executing the computer program 530, implements the functions of the modules/units in the above-mentioned device embodiments, such as the functions of the units 410 to 450 shown in fig. 4.

Illustratively, the computer program 530 may be partitioned into one or more modules/units that are stored in the memory 520 and executed by the processor 510 to accomplish the present application. The one or more modules/units may be a series of computer program instruction segments capable of performing specific functions, which are used to describe the execution of the computer program 530 in the electronic device 500.

The electronic device 500 may be a desktop computer, a notebook, a palm computer, a cloud server, or other computing devices. The electronic device may include, but is not limited to, a processor 510, a memory 520. Those skilled in the art will appreciate that fig. 5 is only an example of an electronic device 500 and does not constitute a limitation of the electronic device 500 and may include more or fewer components than shown, or some components may be combined, or different components, e.g., the electronic device may also include input-output devices, network access devices, buses, etc.

The Processor 510 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

The storage 520 may be an internal storage unit of the electronic device 500, such as a hard disk or a memory of the electronic device 500. The memory 520 may also be an external storage device of the electronic device 500, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, which are provided on the electronic device 500. Further, the memory 520 may also include both an internal storage unit and an external storage device of the electronic device 500. The memory 520 is used for storing the computer programs and other programs and data required by the electronic device. The memory 520 may also be used to temporarily store data that has been output or is to be output.

It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-mentioned functions. Each functional unit and module in the embodiments may be integrated in one processing unit, or each unit may exist alone physically, or two or more units are integrated in one unit, and the integrated unit may be implemented in a form of hardware, or in a form of software functional unit. In addition, specific names of the functional units and modules are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present application. The specific working processes of the units and modules in the system may refer to the corresponding processes in the foregoing method embodiments.

In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to the related descriptions of other embodiments for parts that are not described or illustrated in a certain embodiment.

Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

In the embodiments provided in the present application, it should be understood that the disclosed apparatus/electronic device and method may be implemented in other ways. For example, the above-described apparatus/electronic device embodiments are merely illustrative, and for example, the division of the modules or units is only one logical division, and there may be other divisions when actually implemented, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The above units can be implemented in the form of hardware, and also can be implemented in the form of software.

The integrated modules/units, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. Based on such understanding, all or part of the flow in the method of the embodiments described above can be realized by a computer program, which can be stored in a computer-readable storage medium and can realize the steps of the embodiments of the methods described above when the computer program is executed by a processor. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like. It should be noted that the computer readable medium may contain content that is subject to appropriate increase or decrease as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable media does not include electrical carrier signals and telecommunications signals as is required by legislation and patent practice.

The above-mentioned embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present application and are intended to be included within the scope of the present application.